Comments (6)
chychen
commented on August 25, 2024
thanks for being interested in our work.
- about the mp4 generation failure, I think it might relate to the development environment, it was tested 4 years ago.
- about training time, it should be finished in a few hours with a single V100 GPU, something wrong there, however, the project had been no longer maintained, I could not give you any helpful comments.
- about data collection, we randomly trim the sequences into fixed lengths for training.
btw, I think you might also be interested in another work based on imitation learning and reinforcement learning, please checkout out https://github.com/chychen/RL_strategies. (However, again it had been no longer maintained since 3 years ago.)
thanks again, and good luck with your research.
from basketballgan.
TQG1997
commented on August 25, 2024
Thank you very much. You can still reply to my questions！
…------------------ 原始邮件 ------------------
发件人: "Jay ***@***.***>;
发送时间: 2022年6月28日(星期二) 下午3:33
收件人: ***@***.***>;
抄送: ***@***.***>; ***@***.***>;
主题: Re: [chychen/BasketballGAN] Results of data training (Issue #5)
感谢您对我们的工作感兴趣。
关于 mp 4 一代的失败，我觉得可能和开发环境有关， 4 年前就测试过了。
关于训练时间，它应该在几个小时内完成与一个单一的 V100 GPU ，有些错误那里，然而，该项目已经不再维护。
关于数据汇集，我们随机修剪成固定长度的序列进行训练。
btw ，我想你可能也会对另一个基于模仿学习和强化学习的作品感兴趣，请去看看https://github.com/chychen/RL_strategies.（然而，再次，它已不再维持自 3 年前。
再次感谢，祝你研究顺利。
—
直接回复此邮件，在 GitHub 上查看或取消订阅.
您收到这个消息是因为您创建了这个线程。留言 ID ***@***.***与>
from basketballgan.
TQG1997
commented on August 25, 2024
According to this picture, how long did it take you to reach 200K epochs
from basketballgan.
chychen
commented on August 25, 2024
Sorry, I can't remember, it should be less than 6 hours in single 1080Ti or 2080Ti.
from basketballgan.
TQG1997
commented on August 25, 2024
我想拜读一下您的《生成對抗網路應用於籃球防守戰術生成》这篇文章，能否将PDF文件发到我的邮箱 ***@***.***
…------------------ 原始邮件 ------------------
发件人: "chychen/BasketballGAN" ***@***.***>;
发送时间: 2022年7月4日(星期一) 中午11:55
***@***.***>;
***@***.******@***.***>;
主题: Re: [chychen/BasketballGAN] Results of data training (Issue #5)
Sorry, I can't remember, it should be less than 6 hours in single 1080Ti or 2080Ti.
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: ***@***.***>
from basketballgan.
chychen
commented on August 25, 2024
@TQG1997 FYI
https://github.com/chychen/bball_defensive_strategies_generation
https://github.com/chychen/RL_strategies
https://github.com/chychen/BasketballGAN
from basketballgan.
Related Issues (7)
- Dataset documentation HOT 6
- How do you run the GAN? HOT 4
- Inquiry about the Dataset and some metrics HOT 6
- Data training HOT 4
- 训练过程如果中断了，能否恢复训练
- I used the following commands to train, but the training time was much longer than expected. How did you train？ python Train_Triple.py --folder_path='tmp' --data_path='data' HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from basketballgan.